Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports anthropic/@anthropic-ai/sdk/claudeagentsdk, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports openai/other AI SDK, general programming, or ML/data-science tasks.
Replace with a clear description of what this skill does and when the AI assistant should use it. Include trigger phrases like "when user says X" to help with activation.
Example skills from Anthropic demonstrating various capabilities including skill creation, MCP building, visual design, algorithmic art, internal communications, web testing, artifact building, Slack GIFs, and theme styling.
Software engineering workflow skills: code review, Git workflow, API design, Docker Compose generation, database schema design, CI/CD pipelines, GitLab CI with Kiro CLI headless AI jobs and MCP integration, Terraform modules, Python project setup, test generation, and Kiro project setup.
★not rated 12 1mo agoA
tokens not measured
originalMIT
Scrum + DevSecOps role skills and FSI compliance: threat modeling, security story writing, user story writing, sprint planning with security debt, sprint security review, and PCI-DSS/MAS TRM compliance checking.
★not rated 12 1mo agoA
tokens not measured
originalMIT
MCP server "awslabs.aws-security-posture-advisor" as configured in timwukp/aws-security-posture-advisor-mcp. Runs locally from the awslabs.aws-security-posture-advisor Python package.
★not rated 1 5mo agoA
tokens not measured
originalApache-2.0
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: